stable-baselines3

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

Deep Reinforcement Learning for Robotic Grasping from Octrees

⚡ ⚡ Deep RL (PPO) agent that manages a Uniswap V3 concentrated liquidity position, deciding when to hold, collect fees, or rebalance. Trained and validated against real on-chain data

🚗 This repository offers a ready-to-use training and evaluation environment for conducting various experiments using Deep Reinforcement Learning (DRL) in the CARLA simulator with the help of Stable Baselines 3 library.

Our codebase trials provide an implementation of the Select and Trade paper, which proposes a new paradigm for pair trading using hierarchical reinforcement learning. It includes the code for the proposed method and experimental results on real-world stock data to demonstrate its effectiveness.

Train quadruped locomotion using reinforcement learning in Mujoco

Code base for SICNav T-RO paper and SICNav-Diffusion RA-L paper

Deep Reinforcement Learning based autonomous navigation for quadcopters using PPO algorithm.

Modular DRL framework for autonomous robot navigation in ROS2. Plug-and-play RL backends (Stable-Baselines3, DreamerV3), composable reward functions, observation spaces & neural architectures - built for research and deployment.

This repository contains an application using ROS2 Humble, Gazebo, OpenAI Gym and Stable Baselines3 to train reinforcement learning agents for a path planning problem.

OpenAI Gym environment solutions using Deep Reinforcement Learning.

SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.

OpenAI Gym environment designed for training RL agents to control the flight of a two-dimensional drone.

My implementation of a reinforcement learning model using Stable-Baselines3 to play the NES Super Mario Bros.

Stable-Baselines3 (SB3) reinforcement learning tutorial for the Reinforcement Learning Virtual School 2021.

RL stock selection for China A-share — bundled polars-native factor library (105 Alpha101 + 191 GTJA Alpha191 = 296 factors), board-aware price limits, GPU train + ONNX CPU infer, MIT-licensed.

Deep Reinforcement Learning (DRL) stock trading system with LSTM-PPO, integrating technical indicators and FinBERT-based news sentiment analysis.

Implementation of Jump-Start Reinforcement Learning (JSRL) with Stable Baselines3

Using deep reinforcement learning to train drones to fly autonomously.

A PyTorch implementation of the IEEE WCNC 2025 paper "Worst-Case MSE Minimization for RIS-Assisted mmWave MU-MISO Systems With Hardware Impairments and Imperfect CSI"